© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 8729
    Prev
    Next
    INDEX
    Explanations

    programming structures related to object representation and data handling within code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    сну
    -0.40
     pure
    -0.40
    MenuInflater
    -0.39
     indeed
    -0.39
    goc
    -0.38
    ⓘ
    -0.37
    ParallelGroup
    -0.36
    indeed
    -0.35
     boy
    -0.35
     lustig
    -0.35
    POSITIVE LOGITS
    class
    1.70
     class
    1.63
     classes
    1.07
     clase
    1.03
     classe
    1.00
     CLASS
    0.95
     Class
    0.93
     klasse
    0.93
     Klasse
    0.91
    クラス
    0.91
    Activations Density 0.136%

    No Known Activations